In Class Exercise: 18-10-2023

Loading Packages

library(tidyverse)

── Attaching core tidyverse packages ─────────────────────────────────── tidyverse 2.0.0 ──
✔ dplyr     1.1.3     ✔ readr     2.1.4
✔ forcats   1.0.0     ✔ stringr   1.5.0
✔ ggplot2   3.4.4     ✔ tibble    3.2.1
✔ lubridate 1.9.3     ✔ tidyr     1.3.0
✔ purrr     1.0.2     ── Conflicts ───────────────────────────────────────────────────── tidyverse_conflicts() ──
✖ dplyr::filter() masks stats::filter()
✖ dplyr::lag()    masks stats::lag()
ℹ Use the ]8;;http://conflicted.r-lib.org/conflicted package]8;; to force all conflicts to become errors

library(dplyr)
library(sf)

Linking to GEOS 3.11.2, GDAL 3.6.2, PROJ 9.2.0; sf_use_s2() is TRUE

library(janitor)

Attaching package: ‘janitor’

The following objects are masked from ‘package:stats’:

    chisq.test, fisher.test

library(here)

here() starts at C:/Users/lucas/OneDrive/Desktop/ds_241_f23

Loading Data

bikeshare_sept23 <- read.csv(here("data_raw", "202309-capitalbikeshare-tripdata.csv"))

Slicing off first 10000 points to examine

bikeshare_sept2302 = bikeshare_sept23  |>
  slice(1:100000) 

Plotting Points on standard grid

  ggplot(bikeshare_sept2302, mapping = aes(x = start_lng, y = start_lat))+
  geom_point()

Preparing points for map plotting

points = st_as_sf(bikeshare_sept2302, coords = c("start_lng", "start_lat"), crs = 4326)
plot(st_geometry(points), pch = 16, col = "navy")

Plotting all points on the D.C. map

library(OpenStreetMap)

upperLeft = c(39.12, -77.38)

lowerRight = c(38.77, -76.86)

base_map  = openmap(upperLeft, lowerRight, type="osm")

plot(base_map)

points = st_transform(points, osm())

plot(st_geometry(points), pch=16, col="navy", cex=0.5, add=T)

Separating timestamps to access hour

bikeshare_sept2302 <- bikeshare_sept2302 %>%
  separate(started_at, into = c("start_date", "start_time"), sep = 10, remove = FALSE)
bikeshare_sept2302 <- bikeshare_sept2302 %>%
  separate(ended_at, into = c("end_date", "end_time"), sep = 10, remove = FALSE)
bikeshare_sept2302 <- bikeshare_sept2302 %>%
  separate(start_time, into = c("start_hour", "start_inhour"), sep = 3, remove = FALSE)
bikeshare_sept2302 <- bikeshare_sept2302 %>%
  separate(end_time, into = c("end_hour", "end_inhour"), sep = 3, remove = FALSE)

Mutating a new variable to turn string segment into a numeric value

bikeshare_sept2302 <- bikeshare_sept2302 %>%
  mutate(begin_hr = case_when(
    start_hour == " 01" ~ 01,
    start_hour == " 02" ~ 02,
    start_hour == " 03" ~ 03,
    start_hour == " 04" ~ 04,
    start_hour == " 05" ~ 05,
    start_hour == " 06" ~ 06,
    start_hour == " 07" ~ 07,
    start_hour == " 08" ~ 08,
    start_hour == " 09" ~ 09,
    start_hour == " 10" ~ 10,
    start_hour == " 11" ~ 11,
    start_hour == " 12" ~ 12,
    start_hour == " 13" ~ 13,
    start_hour == " 14" ~ 14,
    start_hour == " 15" ~ 15,
    start_hour == " 16" ~ 16,
    start_hour == " 17" ~ 17,
    start_hour == " 18" ~ 18,
    start_hour == " 19" ~ 19,
    start_hour == " 20" ~ 20,
    start_hour == " 21" ~ 21,
    start_hour == " 22" ~ 22,
    start_hour == " 23" ~ 23,
    start_hour == " 00" ~ 00
  ))

Grouping hours into morning and afternoon

bikeshare_sept2302 <- bikeshare_sept2302 %>%
  mutate(tod = case_when(
  begin_hr %in% c(0,1,2,3,4,5) ~ 1,
  begin_hr %in% c(6,7,8,9,10,11) ~ 2,
  begin_hr %in% c(12,13,14,15,16,17) ~ 3,
  begin_hr %in% c(18,19,20,21,22,23) ~ 4
    ))

Preparing points to be plotted again

points = st_as_sf(bikeshare_sept2302, coords = c("start_lng", "start_lat"), crs = 4326)
plot(st_geometry(points), pch = 16, col = "navy")

Plotting points again on D.C. map, this time distinguishing them by color, where red is morning and black is afternoon.

palette = c("red", "black", "blue", "green")

names(palette) = unique(points$tod)

upperLeft = c(39.13, -77.38)

lowerRight = c(38.77, -76.84)

base_map  = openmap(upperLeft, lowerRight, type="osm")

plot(base_map)

points = st_transform(points, osm())

plot(st_geometry(points), pch=16, col=palette[points$tod], cex=0.5, add=T)